Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Persian
    -0.07
     Were
    -0.07
     comed
    -0.07
     Different
    -0.07
    协商
    -0.07
    ปลาย
    -0.07
     verb
    -0.06
     (_)
    -0.06
    ARGER
    -0.06
    .[
    -0.06
    POSITIVE LOGITS
    anton
    0.07
    тки
    0.07
    ev
    0.07
    .jsx
    0.07
    традицион
    0.07
     الرو
    0.07
    注意到
    0.07
    &apos
    0.07
    .Qt
    0.07
    (serializer
    0.07
    Act Density 0.030%

    No Known Activations